Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks
Abstract
Kolmogorov-Arnold Networks are a new family of neural network architectures which holds promise for overcoming the curse of dimensionality and has interpretability benefits (Liu et al., 2024). In this paper, we explore the connection between Kolmogorov Arnold Networks (KANs) with piecewise linear (univariate real) functions and ReLU networks. We provide completely explicit constructions to convert a piecewise linear KAN into a ReLU network and vice versa.
Cite
Text
Schoots et al. "Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.Markdown
[Schoots et al. "Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.](https://mlanthology.org/aistats/2025/schoots2025aistats-relating/)BibTeX
@inproceedings{schoots2025aistats-relating,
title = {{Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks}},
author = {Schoots, Nandi and Villani, Mattia Jacopo and Bos, Niels},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
year = {2025},
pages = {199-207},
volume = {258},
url = {https://mlanthology.org/aistats/2025/schoots2025aistats-relating/}
}